Showing papers by "Giuseppe De Pietro published in 2007"

A wavelet-based algorithm for multimodal medical image fusion

Abstract: Medical images coming from different sources can often provide different information So, combining two or more co-registered multimodal medical images into a single image (image fusion) is an important support to the medical diagnosis Most of the used image fusion techniques are based on the Multiresolution Analysis (MRA), which is able to decompose an image into several components at different scales This paper presents a novel Wavelet-based method to fuse medical images according to the MRA approach, that aims to put the right "semantic" content in the fused image by applying two different quality indexes: variance and modulus maxima Experimental tests show very encouraging results in terms of both quantitative and qualitative evaluations

Automatic execution of tasks in MiPeG

Abstract: Grid computing and pervasive computing have rapidly emerged and affirmed respectively as the paradigm for high performance computing and the paradigm for user-friendly computing. The conjunction of such paradigms are now generating a new one, the Pervasive Grid Computing, which aims at extending classic grids with characteristics of pervasive computing like spontaneous and transparent integration of mobile devices, context-awareness, proactivity, and so on. In this paper, we present mechanisms and a software infrastructure for executing tasks in a pervasive grid. In particular, the proposed solution, which provides an implementation of the Utility Computing model, enables users to submit tasks and to pick up results without concerning on requiring and handling hardware resources.

A context service for multimodal pervasive environments

Abstract: Pervasive computing environments can proficiently benefit from a new generation of multimodal systems and services, which enable users to interact in natural ways like voice, gesture, facial motions, and so on However, in order to make this possible, it is necessary to integrate such systems and services, possibly in a transparent way, in the environments In addition to this, it is important to note that the presence of multimodal systems of interaction deeply affects the concept of context For this reason, in the present paper, we present new aspects for the concept of context that emerge in a multimodal pervasive environment Such new characteristics have been pointed out and modeled by means of an ontology and rules based approach Specifically, the SOUPA ontology, which is a standard ontology for pervasive environments, have been extended and specified to take care of both hardware devices and software services for multimodal interactions As well, several rules have been defined in order to make environments able to proactively use the best interaction system with respect to user and environment context Definitively, we have designed and developed an ontology-based service that i) exploits OWL ontologies and SWRL rules, ii) integrates them in a software component for multimodal pervasive environment, and iii) performs logic and reasoning mechanisms, in order to proactively handle multimodal systems for user interactions

A web services based architecture for supporting mobile users in large enterprises

Abstract: Business enterprises can proficiently benefit from Ubiquitous Computing (UbiComp) UbiComp environments enable mobile users to access services and resources in a transparent and spontaneous way, that is, without any configuration operation and through very friendly user-environment interface mechanisms which sometimes anticipate user needs Unfortunately, until now the UbiComp model has been applied only to environments bounded to a specific site In order to support large enterprises, which may have several offices spread over a wide geographic area, this model needs to be extended with basic services that enable the realization of federations of environments In other words, in the case of multioffice enterprises, each office could be equipped with a classic UbiComp environment; however, such environments must be interconnected by the internet and co-ordinated by a set of higher level services As a matter of fact, in this case mobile users not only have to get access in a transparent and spontaneous way but, also, they should have the possibility of leaving a physical site without concern of their pending computations and, successively, they should be enabled to come back in the environment, even in a different site, and resume their computations As a consequence, locating mobile users and handling their disconnections becomes a very critical requirement Indeed, differently from a classic UbiComp environment, in a federation of UbiComps resources can not be merely released when a mobile user leaves Instead, the global environment has to infer user's intentions in order to understand whether he will come back to resume computations, or not In this paper, we propose a Web Services based architecture for federating classic UbiComp environments This architecture supports large enterprises with functionalities for locating and tracking mobile users in a federation of UbiComp environments These services implement specific strategies that have been devised to allow i) mobile users to leave a physical site with no concern of their pending computations; ii) the global environment to locate and track users in the federation of UbiComp environments; iii) mobile users to come back in the federation and resume their computations and iv) the environment to reliably handle resources by inferring users intentions

An ontology approach for classification of abnormal white matter in patients with multiple sclerosis

Abstract: Multiple Sclerosis (MS) is an inflammatory autoimmune disease of the Central Nervous System, characterized by development of lesions that cause interference in the communication between brain and the rest of the body Some techniques using numeric algorithms based on mathematical and probabilistic theories are generally used in order to obtain lesions detection In this paper we describe an innovative approach for lesions recognition to be applied after segmentation of brain tissues from quantitive evaluation of MR studies Knowledge about MS lesions is formalized through an ontology and a set of rules: integrating them, automatic inferences can be realized to point out lesions, starting from data about potentially brain abnormal white matter

An ontology-based technique for validation of MRI brain segmentation methods

Abstract: We propose an ontology and rules based approach as innovative instrument to improve and validate brain segmentation in Magnetic Resonance Imaging (MRI), which is a very difficult and time consuming problem. Different techniques are realized to automate segmentation and their development requires a careful evaluation of precision and accuracy. At present segmentation procedures are generally validated by comparison with brain atlas or by use of phantoms. We combine ontology and rules to formalize knowledge about normal and anomalous distribution of brain tissues. Automatic reasoning points out possible "anomalies", imputable to segmentation procedure: in this way the detection and the subsequent solution of bugs become viable.